Model: None
Dataset: The Pile
Neuron 1856 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.5416. Min Act: -0.1700
Data Index: 6786191 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.4006. Min Act: -0.1700
Data Index: 8049024 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.3692. Min Act: -0.1700
Data Index: 8745862 (The Pile)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.3378. Min Act: -0.1700
Data Index: 3054241 (The Pile)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.2278. Min Act: -0.1700
Data Index: 10353155 (The Pile)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.2278. Min Act: -0.1700
Data Index: 9744538 (The Pile)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.2121. Min Act: -0.1700
Data Index: 8285869 (The Pile)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.1964. Min Act: -0.1700
Data Index: 7067026 (The Pile)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.1964. Min Act: -0.1700
Data Index: 6959191 (The Pile)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.1964. Min Act: -0.1700
Data Index: 4858745 (The Pile)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.1964. Min Act: -0.1700
Data Index: 9636526 (The Pile)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.1964. Min Act: -0.1700
Data Index: 1783791 (The Pile)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.1964. Min Act: -0.1700
Data Index: 9263696 (The Pile)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.1806. Min Act: -0.1700
Data Index: 5401005 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.1806. Min Act: -0.1700
Data Index: 1496428 (The Pile)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.1806. Min Act: -0.1700
Data Index: 5585911 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.1806. Min Act: -0.1700
Data Index: 6204613 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.1649. Min Act: -0.1700
Data Index: 4787083 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.1649. Min Act: -0.1700
Data Index: 1999284 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5416. Min Range: -3.5416
Max Act: 3.1492. Min Act: -0.1700
Data Index: 353798 (The Pile)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19